Computer Vision Toolbox
设计和测试计算机视觉，3D视觉和视频处理系统
Computer Vision Toolbox™ provides algorithms, functions, and apps for designing and testing computer vision, 3D vision, and video processing systems. You can perform object detection and tracking, as well as feature detection, extraction, and matching. For 3D vision, the toolbox supports single, stereo, and fisheye camera calibration; stereo vision; 3D reconstruction; and lidar and 3D point cloud processing. Computer vision apps automate ground truth labeling and camera calibration workflows.
You can train custom object detectors using deep learning and machine learning algorithms such as YOLO v2, Faster R-CNN, and ACF. For semantic segmentation you can use deep learning algorithms such as SegNet, U-Net, and DeepLab. Pretrained models let you detect faces, pedestrians, and other common objects.
您可以通过在多核处理器和GPU上运行它们来加速您的算法。大多数工具箱算法支持C / C ++代码生成，用金宝app于与现有代码，桌面原型设计和嵌入式视觉系统部署集成。
开始：
Object Detection and Recognition
框架培训，评估和部署对象探测器，如yolo v2，更快的r-cnn，acf和diusta-jones。对象识别能力包括袋子的视觉单词和OCR。佩带的模型检测面孔，行人和其他常见物体。
Object detection using Faster R-CNN.
Semantic Segmentation
Segment images and 3D volumes by classifying individual pixels and voxels using networks such as SegNet, FCN, U-Net, and DeepLab v3+.
地面真理标签
Automate labeling for object detection, semantic segmentation, and scene classification using the Video Labeler and Image Labeler apps.
与视频贴标程序应用程序标记的地面真相。
Lidar and 3D Point Cloud Processing
段，群集，下拉姆，去噪，寄存器和带有LIDAR或3D点云数据的拟合几何形状。激光雷达的工具箱TM提供设计，分析和测试LIDAR处理系统的其他功能。
Lidar and Point Cloud I/O
从文件，LIDAR和RGB-D传感器读取，写入和显示点云。
点云注册
Register 3D point clouds using Normal-Distributions Transform (NDT), Iterative Closest Point (ICP), and Coherent Point Drift (CPD) algorithms.
注册和缝合一系列点云。
分割和形状配件
Segment point clouds into clusters and fit geometric shapes to point clouds. Segment ground plane in lidar data for automated driving and robotics applications.
Segmented lidar point cloud.
Single Camera Calibration
Automate checkerboard detection and calibrate pinhole and fisheye cameras using the Camera Calibrator app.
Stereo Camera Calibration
校准立体声对以计算深度并重建3D场景。
Stereo camera calibrator app.
立体视觉
Estimate depth and reconstruct a 3D scene using a stereo camera pair.
Stereo disparity map representing relative depths.
Feature Detection, Extraction, and Matching
检测，提取和匹配跨多个图像的诸如Blob，边和角的有趣功能。
使用点特征检测，提取和匹配检测杂乱场景中的物体。
基于功能的图像配准
匹配多个图像的特征来估计图像和寄存器图像序列之间的几何变换。
Panorama created with feature-based registration.
Object Tracking
Track object trajectories from frame to frame in video sequences.
小径表示跟踪对象的轨迹。
运动估计数
Estimate motion between video frames using optical flow, block matching, and template matching.
Detecting moving objects with a stationary camera.
Code Generation
Generate C/C++, CUDA code, and MEX functions for toolbox functions, classes, system objects, and blocks.
Mask-RCNN
Train Mask-RCNN networks for instance segmentation using deep learning
Visual SLAM
管理3-D世界点和投影对应关系到2-D图像点
APRILTAG姿态估计
用于机器人和增强现实ApplicationScamera校准的图像中APRILTAGS姿势
点云注册
Register point clouds using phase correlation for SLAM applications
Point Cloud Loop Closure Detection
点云特征描述符用于SLAM环路闭合检测
Seerelease notesfor details on any of these features and corresponding functions.
